Sökning: onr:"swepub:oai:DiVA.org:kth-285742" >
Human- Versus Machi...
-
Entezarjou, ArtinKarolinska Institutet,Lund University,Lunds universitet,Allmänmedicin och samhällsmedicin,Forskargrupper vid Lunds universitet,Family Medicine and Community Medicine,Lund University Research Groups
(författare)
Human- Versus Machine Learning-Based Triage Using Digitalized Patient Histories in Primary Care : Comparative Study
- Artikel/kapitelEngelska2020
Förlag, utgivningsår, omfång ...
-
2020-09-03
-
JMIR Publications Inc.2020
-
printrdacarrier
Nummerbeteckningar
-
LIBRIS-ID:oai:DiVA.org:kth-285742
-
https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-285742URI
-
https://doi.org/10.2196/18930DOI
-
https://lup.lub.lu.se/record/5b055c28-fabb-4f42-a1d6-8b6b57aadee7URI
-
http://kipublications.ki.se/Default.aspx?queryparsed=id:144921175URI
Kompletterande språkuppgifter
-
Språk:engelska
-
Sammanfattning på:engelska
Ingår i deldatabas
Klassifikation
-
Ämneskategori:ref swepub-contenttype
-
Ämneskategori:art swepub-publicationtype
Anmärkningar
-
QC 20201113
-
Background: Smartphones have made it possible for patients to digitally report symptoms before physical primary care visits. Using machine learning (ML), these data offer an opportunity to support decisions about the appropriate level of care (triage). Objective: The purpose of this study was to explore the interrater reliability between human physicians and an automated ML-based triage method. Methods: After testing several models, a naive Bayes triage model was created using data from digital medical histories, capable of classifying digital medical history reports as either in need of urgent physical examination or not in need of urgent physical examination The model was tested on 300 digital medical history reports and classification was compared with the majority vote of an expert panel of 5 primary care physicians (PCPs). Reliability between raters was measured using both Cohen kappa (adjusted for chance agreement) and percentage agreement (not adjusted for chance agreement). Results: Interrater reliability as measured by Cohen kappa was 0.17 when comparing the majority vote of the reference group with the model. Agreement was 74% (138/186) for cases judged not in need of urgent physical examination and 42% (38/90) for cases judged to be in need of urgent physical examination No specific features linked to the model's triage decision could be identified. Between physicians within the panel, Cohen kappa was 0.2. Intrarater reliability when 1 physician retriaged 50 reports resulted in Cohen kappa of 0.55. Conclusions: Low interrater and intrarater agreement in triage decisions among PCPs limits the possibility to use human decisions as a reference for ML to automate triage in primary care.
Ämnesord och genrebeteckningar
Biuppslag (personer, institutioner, konferenser, titlar ...)
-
Bonamy, Anna-Karin EdstedtKarolinska Institutet,Doctrin AB
(författare)
-
Benjaminsson, SimonSmartera AB, Stockholm, Sweden.
(författare)
-
Herman, Pawel,1979-KTH Royal Institute of Technology,KTH,Beräkningsvetenskap och beräkningsteknik (CST)(Swepub:kth)u19pqm1e
(författare)
-
Midlöv, PatrikLund University,Lunds universitet,Institutionen för kliniska vetenskaper, Malmö,Medicinska fakulteten,Allmänmedicin och samhällsmedicin,Forskargrupper vid Lunds universitet,Department of Clinical Sciences, Malmö,Faculty of Medicine,Family Medicine and Community Medicine,Lund University Research Groups(Swepub:lu)klin-pmi
(författare)
-
Allmänmedicin och samhällsmedicinForskargrupper vid Lunds universitet
(creator_code:org_t)
Sammanhörande titlar
-
Ingår i:JMIR Medical Informatics: JMIR Publications Inc.8:92291-9694
Internetlänk
Hitta via bibliotek
Till lärosätets databas